DeepAI
Log In Sign Up

Empirical Evaluation of Biased Methods for Alpha Divergence Minimization

05/13/2021
by   Tomas Geffner, et al.
0

In this paper we empirically evaluate biased methods for alpha-divergence minimization. In particular, we focus on how the bias affects the final solutions found, and how this depends on the dimensionality of the problem. We find that (i) solutions returned by these methods appear to be strongly biased towards minimizers of the traditional "exclusive" KL-divergence, KL(q||p), and (ii) in high dimensions, an impractically large amount of computation is needed to mitigate this bias and obtain solutions that actually minimize the alpha-divergence of interest.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/19/2020

On the Difficulty of Unbiased Alpha Divergence Minimization

Several approximate inference algorithms have been proposed to minimize ...
05/01/2015

Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions

Many standard optimization methods for segmentation and reconstruction c...
10/15/2020

Non-saturating GAN training as divergence minimization

Non-saturating generative adversarial network (GAN) training is widely u...
05/09/2018

Description of a Tracking Metric Inspired by KL-divergence

A unified metric is given for the evaluation of tracking systems. The me...
08/23/2020

Learn to Talk via Proactive Knowledge Transfer

Knowledge Transfer has been applied in solving a wide variety of problem...
08/29/2018

Centroid estimation based on symmetric KL divergence for Multinomial text classification problem

We define a new method to estimate centroid for text classification base...